Title :
Focal-plane optical flow computation by foveated CNNs
Author_Institution :
Rome Univ., Italy
Abstract :
Optical flow computation is instrumental in robot guidance. Optoelectronic smart-pixel sensors for such computation may be realized on a single chip, by making use of a suitable cellular neural network architecture defined on a log-polar space-variant grid. Simulations confirm validity of the filtering system, and possible realizable structures are discussed
Keywords :
cellular neural nets; computerised navigation; focal planes; image sequences; integrated optoelectronics; intelligent sensors; neural chips; robot vision; cellular neural network architecture; filtering system; focal-plane optical flow computation; foveated CNN; log-polar space-variant grid; optoelectronic smart-pixel sensors; robot guidance; Cellular neural networks; Computer networks; Image motion analysis; Instruments; Optical computing; Optical filters; Optical sensors; Optoelectronic and photonic sensors; Orbital robotics; Robot sensing systems;
Conference_Titel :
Cellular Neural Networks and Their Applications Proceedings, 1998 Fifth IEEE International Workshop on
Conference_Location :
London
Print_ISBN :
0-7803-4867-2
DOI :
10.1109/CNNA.1998.685354
